Classification method and system for grid-connected working conditions of energy storage system, storage medium and server
A technology of an energy storage system and a classification method, which is applied to storage media and servers, a classification method for grid-connected working conditions of an energy storage system, and the system field, can solve problems such as difficulty in guaranteeing accuracy and complex and changeable grid-connected working conditions.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0057] see figure 1 , a method for classifying grid-connected working conditions of an energy storage system according to an embodiment of the present invention includes the following steps:
[0058] S1. Collect the data of the grid-connected operation condition of the energy storage power station;
[0059] S2. Obtain the data set to be classified by preprocessing the data of the grid-connected operation condition of the energy storage power station;
[0060] S3. Input the data set to be classified into the pre-built random forest classification model to determine whether it is necessary to analyze the influence of characteristic parameters. If not, the random forest classification model directly outputs the classification results of the grid-connected conditions of the energy storage system; if necessary , firstly calculate the VIM of the feature parameter importance of the working condition, complete the training of the random forest classification model, and then use the t...
Embodiment 2
[0079] The implementation and effect of the method for classifying the grid-connected working conditions of the energy storage system of the present invention will be described below through practical cases.
[0080] In this example, a total of N=238 groups of data on C=5 actual operating conditions of grid-connected lithium-ion battery energy storage power stations above MW level are collected, 16 groups of auxiliary frequency modulation on the power supply side, 27 groups of combined photovoltaic and storage, wind-storage smoothing and The planned output is 96 and 73 groups, and 26 groups of grid-side peak shaving and valley filling. The energy storage systems of the above five applications operate at a power of 0.1 to 1P 0 , The capacity is 5-80% DOD and the time is in the range of seconds to hours, starting from the magnitude, response speed, working time, waveform characteristics, etc. , select M=20 performance characterization parameter sets X that are closely related t...
Embodiment 3
[0092] The embodiment of the present invention also proposes a classification system for grid-connected working conditions of an energy storage system, including:
[0093] The data acquisition module 1 is used to collect the data of the grid-connected operation condition of the energy storage power station;
[0094] The to-be-classified data set acquisition module 2 is used to obtain the to-be-classified data set by preprocessing the grid-connected operating condition data of the energy storage power station;
[0095] The random forest classification module 3 is used to input the data set to be classified into the pre-built random forest classification model to determine whether it is necessary to analyze the influence of characteristic parameters. If not, the random forest classification model directly outputs the grid connection conditions of the energy storage system If necessary, first calculate the VIM of the feature parameters of the operating conditions, complete the tr...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com